Download Data Mining - Department of Computer Engineering

Data Mining
CE, KMITL 2/2558
©CS
© CS
Data Mining, CE KMITL, 2/2558
2
© CS
Data Mining, CE KMITL, 2/2558
3
© CS
Data Mining, CE KMITL, 2/2558
4
 Midterm
 Final
Exam (written)
Exam (written)
30%
35%
 Project
25%
 Report
5%
5%
 Homework
© CS
Data Mining, CE KMITL, 2/2558
5
 Main
(required)
• Data Mining: Concepts and Techniques,
 Jiawei Han, Micheline Kamber, Jian Pei
 Morgan Kaufmann, 2011
• Predictive analytics and data mining
 Charles Elkan
 2013
© CS
Data Mining, CE KMITL, 2/2558
6

Others
• Data Mining: Practical Machine
Learning Tools and Techniques (3rd ed)
 Witten, Frank and Hall
 Morgan Kaufmann, 2011
• Big Data, Data Mining and
Machine Learning
 Jared Dean
 Wiley, 2014
© CS
Data Mining, CE KMITL, 2/2558
7
• Introduction to Data Mining
 Tan, Steinbach and Kumar
 Addison Wesley, 2005
 Course
gg drive
• https://drive.google.com/open?id=0B4uL6TyM1-NZldfT3I0bjJkT2s
© CS
Data Mining, CE KMITL, 2/2558
8
 Rapid
Miner
• http://www.rapidminer.com/
--------------------------------------------- KNIME
• https://www.knime.org/knime
 Weka
• http://www.cs.waikato.ac.nz/ml/weka
R
• http://cran.r-project.org/
© CS
Data Mining, CE KMITL, 2/2558
9
 http://archive.ics.uci.edu/ml/
 http://www.inf.ed.ac.uk/teaching/courses/
dme/html/datasets0405.html
 http://www.kdnuggets.com/
 http://www.sigkdd.org/kddcup/index.php
© CS
Data Mining, CE KMITL, 2/2558
10
 ชุตเิ มษฏ์ ศรีนล
ิ ทา
 ECC
914
 [email protected]
• with mail topic prefix “<< DM582 >>”
 Wednesday
© CS
morning or by appointment
Data Mining, CE KMITL, 2/2558
11
 ทําความเข้าใจกับเรื่องต่อไปนี้
• Data Mining
• Statistics
• Machine Learning
ค้นคว้าจาก internet หรือหนังสือ มากกว่าหนึง่ แหล่งข้อมูล
ทัง้ นีใ้ ห้เขียนสรุปอธิบายให้เข้าใจว่าคืออะไร มีความสัมพันธ์กนั หรือไม่
อย่างไร ทัง้ นีใ้ ห้ระบุ source ของข้อมูลด้วย
*** ไม่ยาก ห้ามลอกกัน ***
© CS
Data Mining, CE KMITL, 2/2558
12
 4-5
persons per group
 Study and choose a topic from KDD cup
competition (or other data source)
• http://www.sigkdd.org/kddcup/index.php
• https://www.kaggle.com/c/kdd-cup-2014predicting-excitement-at-donors-choose
• https://www.kddcup2012.org/
 Prepare
away)
© CS
project proposal (due Two Fridays
Data Mining, CE KMITL, 2/2558
13
 Inidividual
 Find
a big data analytics success story
that interests you
 Share
it with the rest of the class
 10-minute
© CS
talk & report
Data Mining, CE KMITL, 2/2558
14
https://youtu.be/t4wtzIuoY0w
Data Mining, CE KMITL, 2/2558
© CS
15

Data mining (knowledge discovery from data)
• Extraction of interesting (non-trivial, implicit, previously
unknown and potentially useful) patterns or knowledge from
huge amount of data

Alternative names
• Knowledge discovery in databases (KDD), knowledge
extraction, data/pattern analysis, data archeology, data
dredging, information harvesting, business intelligence, etc.

Watch out: Is everything “data mining”?
• Simple search and query processing
• (Deductive) expert systems
© CS
Data Mining, CE KMITL, 2/2558
46
6
7
5
3
4
 Data
mining
• Core of KDD
• Search for
knowledge in the
data
1
2
© CS
Data Mining, CE KMITL, 2/2558
47

Data mining may generate thousands of patterns: Not
all of them are interesting
• Suggested approach: Human-centered, query-based, focused
mining

Interestingness measures
• A pattern is interesting if it is easily understood by humans,
valid on new or test data with some degree of certainty,
potentially useful, novel, or validates some hypothesis that a
user seeks to confirm

Objective vs. subjective interestingness measures
• Objective: based on statistics and structures of patterns, e.g.,
support, confidence, etc.
• Subjective: based on user’s belief in the data, e.g.,
unexpectedness, novelty, actionability, etc.
© CS
Data Mining, CE KMITL, 2/2558
48

Find all the interesting patterns: Completeness
• Can a data mining system find all the interesting patterns? Do
we need to find all of the interesting patterns?
• Heuristic vs. exhaustive search
• Association vs. classification vs. clustering

Search for only interesting patterns: An optimization
problem
• Can a data mining system find only the interesting patterns?
• Approaches
 First general all the patterns and then filter out the uninteresting
ones
 Generate only the interesting patterns—mining query optimization
© CS
Data Mining, CE KMITL, 2/2558
49

Precise patterns vs. approximate patterns
• Association and correlation mining: possible find sets of
precise patterns
 But approximate patterns can be more compact and sufficient
 How to find high quality approximate patterns??
• Gene sequence mining: approximate patterns are
inherent
 How to derive efficient approximate pattern mining
algorithms??

Constrained vs. non-constrained patterns
• Why constraint-based mining?
• What are the possible kinds of constraints? How to push
constraints into the mining process?
© CS
Data Mining, CE KMITL, 2/2558
50
Graphical User Interface
Pattern Evaluation
Data Mining Engine
Knowl
edgeBase
Database or Data
Warehouse Server
data cleaning, integration, and selection
Database
© CS
Data
World-Wide Other Info
Repositories
Warehouse
Web
Data Mining, CE KMITL, 2/2558
51
Increasing potential
to support
business decisions
Decision
Making
Data Presentation
Visualization Techniques
End User
Business
Analyst
Data Mining
Information Discovery
Data
Analyst
Data Exploration
Statistical Summary, Querying, and Reporting
Data Preprocessing/Integration, Data Warehouses
Feature Selection, Dimensionality Reduction, Normalization
Data Sources
Paper, Files, Web documents, Scientific experiments, Database Systems
© CS
Data Mining, CE KMITL, 2/2558
DBA
52
Database
Technology
Machine
Learning
Pattern
Recognition
© CS
Statistics
Data Mining
Algorithm
Data Mining, CE KMITL, 2/2558
Visualization
Other
Disciplines
53

Tremendous amount of data
• Algorithms must be highly scalable to handle such as tera-bytes of data

High-dimensionality of data
• Micro-array may have tens of thousands of dimensions

High complexity of data
•
•
•
•
•
•

© CS
Data streams and sensor data
Time-series data, temporal data, sequence data
Structure data, graphs, social networks and multi-linked data
Heterogeneous databases and legacy databases
Spatial, spatiotemporal, multimedia, text and Web data
Software programs, scientific simulations
New and sophisticated applications
Data Mining, CE KMITL, 2/2558
54

Data to be mined
• Relational, data warehouse, transactional, stream, objectoriented/relational, active, spatial, time-series, text, multi-media,
heterogeneous, legacy, WWW

Knowledge to be mined
• Characterization, discrimination, association, classification, clustering,
trend/deviation, outlier analysis, etc.
• Multiple/integrated functions and mining at multiple levels

Techniques utilized
• Database-oriented, data warehouse (OLAP), machine learning,
statistics, visualization, etc.

Applications adapted
• Retail, telecommunication, banking, fraud analysis, bio-data mining,
stock market analysis, text mining, Web mining, etc.
© CS
Data Mining, CE KMITL, 2/2558
55
 General
functionality
• Descriptive data mining
• Predictive data mining
 Different
views lead to different
classifications
• Data view: Kinds of data to be mined
• Knowledge view: Kinds of knowledge to be
discovered
• Method view: Kinds of techniques utilized
• Application view: Kinds of applications adapted
© CS
Data Mining, CE KMITL, 2/2558
56

Database-oriented data sets and applications
• Relational database, data warehouse, transactional database

Advanced data sets and advanced applications
• Data streams and sensor data
• Time-series data, temporal data, sequence data (incl. biosequences)
• Structure data, graphs, social networks and multi-linked data
• Object-relational databases
• Heterogeneous databases and legacy databases
• Spatial data and spatiotemporal data
• Multimedia database
• Text databases
• The World-Wide Web
© CS
Data Mining, CE KMITL, 2/2558
57

Multidimensional concept description:
Characterization and discrimination
• Generalize, summarize, and contrast data characteristics,
e.g., dry vs. wet regions

Frequent patterns, association, correlation vs.
causality
• Diaper  Beer [0.5%, 75%] (Correlation or causality?)

Classification and prediction
• Construct models (functions) that describe and
distinguish classes or concepts for future prediction
 E.g., classify countries based on (climate), or classify cars
based on (gas mileage)
• Predict some unknown or missing numerical values
© CS
Data Mining, CE KMITL, 2/2558
58

Cluster analysis
• Class label is unknown: Group data to form new classes, e.g., cluster
houses to find distribution patterns
• Maximizing intra-class similarity & minimizing interclass similarity

Outlier analysis
• Outlier: Data object that does not comply with the general behavior of
the data
• Noise or exception? Useful in fraud detection, rare events analysis

Trend and evolution analysis
•
•
•
•

© CS
Trend and deviation: e.g., regression analysis
Sequential pattern mining: e.g., digital camera  large SD memory
Periodicity analysis
Similarity-based analysis
Other pattern-directed or statistical analyses
Data Mining, CE KMITL, 2/2558
59

Identify dependencies in the data:
• X makes Y likely

Indicate significance of each dependency

Bayesian methods
Uses:

Targeted marketing
“Find groups of items
commonly purchased
together”
© CS
Data Mining, CE KMITL, 2/2558
60
Find groups of similar data items
 Statistical techniques require some definition of
“distance” (e.g. between travel profiles) while
conceptual techniques use background concepts
and logical descriptions
Uses:
 Demographic analysis
Technologies:
 Self-Organizing Maps
 Probability Densities
“Group people with
similar travel profiles”
 Conceptual Clustering

© CS
Data Mining, CE KMITL, 2/2558
61

Find ways to separate data items into pre-defined
groups
• We know X and Y belong together, find other things in same
group

Requires “training data”: Data items where group is
known
Uses:

Profiling
Technologies:


© CS
Generate decision trees
(results are human understandable)
Neural Nets
Data Mining, CE KMITL, 2/2558
“Route documents to
most likely interested
parties”
62

Classification
• #1. C4.5: Quinlan, J. R. C4.5: Programs for Machine Learning. Morgan
Kaufmann., 1993.
• #2. CART: L. Breiman, J. Friedman, R. Olshen, and C. Stone. Classification and
Regression Trees. Wadsworth, 1984.
• #3. K Nearest Neighbours (kNN): Hastie, T. and Tibshirani, R. 1996. Discriminant
Adaptive Nearest Neighbor Classification. TPAMI. 18(6)
• #4. Naive Bayes Hand, D.J., Yu, K., 2001. Idiot's Bayes: Not So Stupid After All?
Internat. Statist. Rev. 69, 385-398.

Statistical Learning
• #5. SVM: Vapnik, V. N. 1995. The Nature of Statistical Learning Theory. SpringerVerlag.
• #6. EM: McLachlan, G. and Peel, D. (2000). Finite Mixture Models. J. Wiley, New
York. Association Analysis
• #7. Apriori: Rakesh Agrawal and Ramakrishnan Srikant. Fast Algorithms for
Mining Association Rules. In VLDB '94.
• #8. FP-Tree: Han, J., Pei, J., and Yin, Y. 2000. Mining frequent patterns without
candidate generation. In SIGMOD '00.
© CS
Data Mining, CE KMITL, 2/2558
63

Link Mining
• #9. PageRank: Brin, S. and Page, L. 1998. The anatomy of a large-scale
hypertextual Web search engine. In WWW-7, 1998.
• #10. HITS: Kleinberg, J. M. 1998. Authoritative sources in a hyperlinked
environment. SODA, 1998.

Clustering
• #11. K-Means: MacQueen, J. B., Some methods for classification and
analysis of multivariate observations, in Proc. 5th Berkeley Symp.
Mathematical Statistics and Probability, 1967.
• #12. BIRCH: Zhang, T., Ramakrishnan, R., and Livny, M. 1996. BIRCH: an
efficient data clustering method for very large databases. In SIGMOD
'96.

Bagging and Boosting
• #13. AdaBoost: Freund, Y. and Schapire, R. E. 1997. A decision-theoretic
generalization of on-line learning and an application to boosting. J.
Comput. Syst. Sci. 55, 1 (Aug. 1997), 119-139.
© CS
Data Mining, CE KMITL, 2/2558
64

Sequential Patterns
• #14. GSP: Srikant, R. and Agrawal, R. 1996. Mining Sequential Patterns:
Generalizations and Performance Improvements. In Proceedings of the 5th
International Conference on Extending Database Technology, 1996.
• #15. PrefixSpan: J. Pei, J. Han, B. Mortazavi-Asl, H. Pinto, Q. Chen, U. Dayal and MC. Hsu. PrefixSpan: Mining Sequential Patterns Efficiently by Prefix-Projected
Pattern Growth. In ICDE '01.

Integrated Mining
• #16. CBA: Liu, B., Hsu, W. and Ma, Y. M. Integrating classification and association
rule mining. KDD-98.

Rough Sets
• #17. Finding reduct: Zdzislaw Pawlak, Rough Sets: Theoretical Aspects of
Reasoning about Data, Kluwer Academic Publishers, Norwell, MA, 1992

Graph Mining
• #18. gSpan: Yan, X. and Han, J. 2002. gSpan: Graph-Based Substructure Pattern
Mining. In ICDM '02.
© CS
Data Mining, CE KMITL, 2/2558
65

Mining methodology
• Mining different kinds of knowledge from diverse data types, e.g., bio, stream,
Web
• Performance: efficiency, effectiveness, and scalability
• Pattern evaluation: the interestingness problem
• Incorporation of background knowledge
• Handling noise and incomplete data
• Parallel, distributed and incremental mining methods
• Integration of the discovered knowledge with existing one: knowledge fusion

User interaction
• Data mining query languages and ad-hoc mining
• Expression and visualization of data mining results
• Interactive mining of knowledge at multiple levels of abstraction

Applications and social impacts
• Domain-specific data mining & invisible data mining
• Protection of data security, integrity, and privacy
© CS
Data Mining, CE KMITL, 2/2558
66

Data mining and KDD (SIGKDD: CDROM)
•
•

Database systems (SIGMOD: ACM SIGMOD Anthology—CD ROM)
•
•

Conferences: Joint Stat. Meeting, etc.
Journals: Annals of statistics, etc.
Visualization
•
•
© CS
Conferences: SIGIR, WWW, CIKM, etc.
Journals: WWW: Internet and Web Information Systems,
Statistics
•
•

Conferences: Machine learning (ML), AAAI, IJCAI, COLT (Learning Theory), CVPR, NIPS, etc.
Journals: Machine Learning, Artificial Intelligence, Knowledge and Information Systems, IEEE-PAMI, etc.
Web and IR
•
•

Conferences: ACM-SIGMOD, ACM-PODS, VLDB, IEEE-ICDE, EDBT, ICDT, DASFAA
Journals: IEEE-TKDE, ACM-TODS/TOIS, JIIS, J. ACM, VLDB J., Info. Sys., etc.
AI & Machine Learning
•
•

Conferences: ACM-SIGKDD, IEEE-ICDM, SIAM-DM, PKDD, PAKDD, etc.
Journal: Data Mining and Knowledge Discovery, KDD Explorations, ACM TKDD
Conference proceedings: CHI, ACM-SIGGraph, etc.
Journals: IEEE Trans. visualization and computer graphics, etc.
Data Mining, CE KMITL, 2/2558
67

S. Chakrabarti. Mining the Web: Statistical Analysis of Hypertex and Semi-Structured Data. Morgan Kaufmann, 2002

R. O. Duda, P. E. Hart, and D. G. Stork, Pattern Classification, 2ed., Wiley-Interscience, 2000

T. Dasu and T. Johnson. Exploratory Data Mining and Data Cleaning. John Wiley & Sons, 2003


U. M. Fayyad, G. Piatetsky-Shapiro, P. Smyth, and R. Uthurusamy. Advances in Knowledge Discovery and Data Mining.
AAAI/MIT Press, 1996
U. Fayyad, G. Grinstein, and A. Wierse, Information Visualization in Data Mining and Knowledge Discovery, Morgan
Kaufmann, 2001

J. Han and M. Kamber. Data Mining: Concepts and Techniques. Morgan Kaufmann, 2nd ed., 2006

D. J. Hand, H. Mannila, and P. Smyth, Principles of Data Mining, MIT Press, 2001

T. Hastie, R. Tibshirani, and J. Friedman, The Elements of Statistical Learning: Data Mining, Inference, and Prediction,
Springer-Verlag, 2001

B. Liu, Web Data Mining, Springer 2006.

T. M. Mitchell, Machine Learning, McGraw Hill, 1997

G. Piatetsky-Shapiro and W. J. Frawley. Knowledge Discovery in Databases. AAAI/MIT Press, 1991

P.-N. Tan, M. Steinbach and V. Kumar, Introduction to Data Mining, Wiley, 2005

S. M. Weiss and N. Indurkhya, Predictive Data Mining, Morgan Kaufmann, 1998

I. H. Witten and E. Frank, Data Mining: Practical Machine Learning Tools and Techniques with Java Implementations,
© CS Morgan Kaufmann, 2nd ed. 2005
Data Mining, CE KMITL, 2/2558
68





Data mining: Discovering interesting patterns from large amounts
of data
A natural evolution of database technology, in great demand, with
wide applications
A KDD process includes data cleaning, data integration, data
selection, transformation, data mining, pattern evaluation, and
knowledge presentation
Mining can be performed in a variety of information repositories
Data mining functionalities: characterization, discrimination,
association, classification, clustering, outlier and trend analysis,
etc.

Data mining systems and architectures

Major issues in data mining
Data Mining, CE KMITL, 2/2558
© CS
69